{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention/papers/240","list_of":"/method/attention","method":"Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":240,"pages_in_order":316,"rows_per_page":100,"rows":[23901,24000],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention","prev":"/method/attention/papers/239","next":"/method/attention/papers/241","papers":[{"paper":null,"slug":"rafola-a-rationale-annotated-corpus-for","title":"RaFoLa: A Rationale-Annotated Corpus for Detecting Indicators of Forced Labour","date":"2022-05-05","arxiv_id":"2205.02684","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-graph-expansion-for-semantics-guided","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","date":"2022-05-05","arxiv_id":"2205.02958","n_code_links":0,"syntology":null},{"paper":"/paper/hyperbolic-relevance-matching-for-neural","slug":"hyperbolic-relevance-matching-for-neural","title":"Hyperbolic Relevance Matching for Neural Keyphrase Extraction","date":"2022-05-04","arxiv_id":"2205.02047","n_code_links":1,"syntology":null},{"paper":"/paper/improving-multi-document-summarization","slug":"improving-multi-document-summarization","title":"Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness","date":"2022-05-04","arxiv_id":"2205.01889","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-of-russian-language","slug":"knowledge-distillation-of-russian-language","title":"Knowledge Distillation of Russian Language Models with Reduction of Vocabulary","date":"2022-05-04","arxiv_id":"2205.02340","n_code_links":1,"syntology":null},{"paper":"/paper/provably-confidential-language-modelling-1","slug":"provably-confidential-language-modelling-1","title":"Provably Confidential Language Modelling","date":"2022-05-04","arxiv_id":"2205.01863","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xuandongzhao/crt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"using-virtual-edges-to-extract-keywords-from","title":"Using virtual edges to extract keywords from texts modeled as complex networks","date":"2022-05-04","arxiv_id":"2205.02172","n_code_links":0,"syntology":null},{"paper":"/paper/better-plain-vit-baselines-for-imagenet-1k","slug":"better-plain-vit-baselines-for-imagenet-1k","title":"Better plain ViT baselines for ImageNet-1k","date":"2022-05-03","arxiv_id":"2205.01580","n_code_links":7,"syntology":{"ran":23,"of":24,"n_ran_checked":20,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/big_vision"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/contrastive-learning-for-prompt-based-few","slug":"contrastive-learning-for-prompt-based-few","title":"Contrastive Learning for Prompt-Based Few-Shot Language Learners","date":"2022-05-03","arxiv_id":"2205.01308","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["yiren-jian/lm-supcon"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-domain-object-detection-with-mean","slug":"cross-domain-object-detection-with-mean","title":"MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer","date":"2022-05-03","arxiv_id":"2205.01643","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-fine-tuning-of-bert-models-on-the","title":"Efficient Fine-Tuning of BERT Models on the Edge","date":"2022-05-03","arxiv_id":"2205.01541","n_code_links":0,"syntology":null},{"paper":null,"slug":"explain-and-conquer-personalised-text-based","title":"Explain and Conquer: Personalised Text-based Reviews to Achieve Transparency","date":"2022-05-03","arxiv_id":"2205.01759","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-patterns-in-knowledge-attribution-for","title":"Finding patterns in Knowledge Attribution for Transformers","date":"2022-05-03","arxiv_id":"2205.01366","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-to-remember-transformer-with-recurrent","title":"Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation","date":"2022-05-03","arxiv_id":"2205.01546","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-effects-transformers-for-hierarchical","slug":"mixed-effects-transformers-for-hierarchical","title":"Mixed-effects transformers for hierarchical adaptation","date":"2022-05-03","arxiv_id":"2205.01749","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-language-taskonomy-which-nlp-tasks-are","title":"Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?","date":"2022-05-03","arxiv_id":"2205.01404","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-issue-types-with-sebert","slug":"predicting-issue-types-with-sebert","title":"Predicting Issue Types with seBERT","date":"2022-05-03","arxiv_id":"2205.01335","n_code_links":1,"syntology":null},{"paper":"/paper/semattack-natural-textual-attacks-via-1","slug":"semattack-natural-textual-attacks-via-1","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-05-03","arxiv_id":"2205.01287","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai-secure/semattack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"synthesized-speech-detection-using","title":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","date":"2022-05-03","arxiv_id":"2205.01800","n_code_links":0,"syntology":null},{"paper":"/paper/textual-entailment-for-event-argument","slug":"textual-entailment-for-event-argument","title":"Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning","date":"2022-05-03","arxiv_id":"2205.01376","n_code_links":1,"syntology":null},{"paper":"/paper/bertops-studying-bert-representations-under-a","slug":"bertops-studying-bert-representations-under-a","title":"BERTops: Studying BERT Representations under a Topological Lens","date":"2022-05-02","arxiv_id":"2205.00953","n_code_links":1,"syntology":null},{"paper":"/paper/centerclip-token-clustering-for-efficient","slug":"centerclip-token-clustering-for-efficient","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","date":"2022-05-02","arxiv_id":"2205.00823","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["mzhaoshuai/CenterCLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/entity-aware-transformers-for-entity-search","slug":"entity-aware-transformers-for-entity-search","title":"Entity-aware Transformers for Entity Search","date":"2022-05-02","arxiv_id":"2205.00820","n_code_links":1,"syntology":null},{"paper":"/paper/improving-students-academic-performance-with","slug":"improving-students-academic-performance-with","title":"Improving Students' Academic Performance with AI and Semantic Technologies","date":"2022-05-02","arxiv_id":"2206.03213","n_code_links":1,"syntology":null},{"paper":"/paper/logiformer-a-two-branch-graph-transformer","slug":"logiformer-a-two-branch-graph-transformer","title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","date":"2022-05-02","arxiv_id":"2205.00731","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-text-classification-using-graph","slug":"multi-task-text-classification-using-graph","title":"Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Language","date":"2022-05-02","arxiv_id":"2205.01204","n_code_links":1,"syntology":null},{"paper":"/paper/opt-open-pre-trained-transformer-language","slug":"opt-open-pre-trained-transformer-language","title":"OPT: Open Pre-trained Transformer Language Models","date":"2022-05-02","arxiv_id":"2205.01068","n_code_links":11,"syntology":{"ran":14,"of":24,"n_ran_checked":14,"n_instrument":0,"unverified":10,"pointer_only":17,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["facebookresearch/metaseq"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"teaching-bert-to-wait-balancing-accuracy-and-1","title":"Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection","date":"2022-05-02","arxiv_id":"2205.00620","n_code_links":0,"syntology":null},{"paper":null,"slug":"aircraft-engine-remaining-useful-life","title":"Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture","date":"2022-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-without-proper-representation","title":"Classification without (Proper) Representation: Political Heterogeneity in Social Media and Its Implications for Classification and Behavioral Analysis","date":"2022-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-covid-19-conspiracy-theories-with","title":"Detecting COVID-19 Conspiracy Theories with Transformers and TF-IDF","date":"2022-05-01","arxiv_id":"2205.00377","n_code_links":0,"syntology":null},{"paper":"/paper/reinforced-swin-convs-transformer-for","slug":"reinforced-swin-convs-transformer-for","title":"Reinforced Swin-Convs Transformer for Underwater Image Enhancement","date":"2022-05-01","arxiv_id":"2205.00434","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["TingdiRen/URSCT-SESR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"coarse-to-fine-video-denoising-with-dual","title":"Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer","date":"2022-04-30","arxiv_id":"2205.00214","n_code_links":0,"syntology":null},{"paper":"/paper/hdgt-heterogeneous-driving-graph-transformer","slug":"hdgt-heterogeneous-driving-graph-transformer","title":"HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding","date":"2022-04-30","arxiv_id":"2205.09753","n_code_links":2,"syntology":null},{"paper":"/paper/storseismic-a-new-paradigm-in-deep-learning","slug":"storseismic-a-new-paradigm-in-deep-learning","title":"StorSeismic: A new paradigm in deep learning for seismic processing","date":"2022-04-30","arxiv_id":"2205.00222","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-contrastive-learning-based","title":"Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection","date":"2022-04-30","arxiv_id":"2205.00122","n_code_links":0,"syntology":null},{"paper":"/paper/exaasc-a-general-target-based-stance","slug":"exaasc-a-general-target-based-stance","title":"ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language","date":"2022-04-29","arxiv_id":"2204.13979","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-from-natural-language-feedback","title":"Training Language Models with Language Feedback","date":"2022-04-29","arxiv_id":"2204.14146","n_code_links":0,"syntology":null},{"paper":null,"slug":"qrelscore-better-evaluating-generated","title":"QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance","date":"2022-04-29","arxiv_id":"2204.13921","n_code_links":0,"syntology":null},{"paper":"/paper/two-new-datasets-for-italian-language","slug":"two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","date":"2022-04-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"controllable-image-captioning","title":"Controllable Image Captioning","date":"2022-04-28","arxiv_id":"2204.13324","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-estimation-with-simplified-transformer","title":"Depth Estimation with Simplified Transformer","date":"2022-04-28","arxiv_id":"2204.13791","n_code_links":0,"syntology":null},{"paper":"/paper/hiner-a-large-hindi-named-entity-recognition","slug":"hiner-a-large-hindi-named-entity-recognition","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","date":"2022-04-28","arxiv_id":"2204.13743","n_code_links":1,"syntology":null},{"paper":"/paper/inferring-implicit-relations-with-language","slug":"inferring-implicit-relations-with-language","title":"Inferring Implicit Relations in Complex Questions with Language Models","date":"2022-04-28","arxiv_id":"2204.13778","n_code_links":1,"syntology":null},{"paper":"/paper/lightweight-bimodal-network-for-single-image","slug":"lightweight-bimodal-network-for-single-image","title":"Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer","date":"2022-04-28","arxiv_id":"2204.13286","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-effect-of-pretraining-corpora-on-in","title":"On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model","date":"2022-04-28","arxiv_id":"2204.13509","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-model-to-synthesize-them-all-multi","title":"One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation","date":"2022-04-28","arxiv_id":"2204.13738","n_code_links":0,"syntology":null},{"paper":null,"slug":"robbertje-a-distilled-dutch-bert-model","title":"RobBERTje: a Distilled Dutch BERT Model","date":"2022-04-28","arxiv_id":"2204.13511","n_code_links":0,"syntology":null},{"paper":"/paper/symmetric-transformer-based-network-for","slug":"symmetric-transformer-based-network-for","title":"Symmetric Transformer-based Network for Unsupervised Image Registration","date":"2022-04-28","arxiv_id":"2204.13575","n_code_links":1,"syntology":null},{"paper":"/paper/tag-assisted-multimodal-sentiment-analysis","slug":"tag-assisted-multimodal-sentiment-analysis","title":"Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities","date":"2022-04-28","arxiv_id":"2204.13707","n_code_links":1,"syntology":null},{"paper":null,"slug":"tailor-a-prompt-based-approach-to-attribute","title":"Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation","date":"2022-04-28","arxiv_id":"2204.13362","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-in-time-series-analysis-a","title":"Transformers in Time-series Analysis: A Tutorial","date":"2022-04-28","arxiv_id":"2205.01138","n_code_links":0,"syntology":null},{"paper":null,"slug":"um6p-cs-at-semeval-2022-task-11-enhancing","title":"UM6P-CS at SemEval-2022 Task 11: Enhancing Multilingual and Code-Mixed Complex Named Entity Recognition via Pseudo Labels using Multilingual Transformer","date":"2022-04-28","arxiv_id":"2204.13515","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-end-to-end-dialogue-summarization-system","title":"An End-to-End Dialogue Summarization System for Sales Calls","date":"2022-04-27","arxiv_id":"2204.12951","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-query-graph-selection-for-knowledge","title":"Better Query Graph Selection for Knowledge Base Question Answering","date":"2022-04-27","arxiv_id":"2204.12662","n_code_links":0,"syntology":null},{"paper":null,"slug":"catrans-context-and-affinity-transformer-for","title":"CATrans: Context and Affinity Transformer for Few-Shot Segmentation","date":"2022-04-27","arxiv_id":"2204.12817","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-2-enhance-knowledge-grounded-dialogue-via","title":"Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling","date":"2022-04-27","arxiv_id":"2204.12681","n_code_links":0,"syntology":null},{"paper":"/paper/modern-baselines-for-sparql-semantic-parsing","slug":"modern-baselines-for-sparql-semantic-parsing","title":"Modern Baselines for SPARQL Semantic Parsing","date":"2022-04-27","arxiv_id":"2204.12793","n_code_links":1,"syntology":null},{"paper":null,"slug":"rigoberta-a-state-of-the-art-language-model","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","date":"2022-04-27","arxiv_id":"2205.10233","n_code_links":0,"syntology":null},{"paper":"/paper/skillspan-hard-and-soft-skill-extraction-from","slug":"skillspan-hard-and-soft-skill-extraction-from","title":"SkillSpan: Hard and Soft Skill Extraction from English Job Postings","date":"2022-04-27","arxiv_id":"2204.12811","n_code_links":1,"syntology":null},{"paper":null,"slug":"timebert-enhancing-pre-trained-language","title":"BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information","date":"2022-04-27","arxiv_id":"2204.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-fast-speech-separation-model-with","title":"Ultra Fast Speech Separation Model with Teacher Student Learning","date":"2022-04-27","arxiv_id":"2204.12777","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-on-attention-mechanisms-for-medical","slug":"a-survey-on-attention-mechanisms-for-medical","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","date":"2022-04-26","arxiv_id":"2204.12406","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-split-fusion-transformer","slug":"adaptive-split-fusion-transformer","title":"Adaptive Split-Fusion Transformer","date":"2022-04-26","arxiv_id":"2204.12196","n_code_links":1,"syntology":null},{"paper":null,"slug":"landing-ai-on-networks-an-equipment-vendor","title":"Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks","date":"2022-04-26","arxiv_id":"2205.08347","n_code_links":0,"syntology":null},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","n_code_links":1,"syntology":null},{"paper":"/paper/plod-an-abbreviation-detection-dataset-for","slug":"plod-an-abbreviation-detection-dataset-for","title":"PLOD: An Abbreviation Detection Dataset for Scientific Documents","date":"2022-04-26","arxiv_id":"2204.12061","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretraining-chinese-bert-for-detecting-word","title":"Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors","date":"2022-04-26","arxiv_id":"2204.12052","n_code_links":0,"syntology":null},{"paper":"/paper/thompson-sampling-for-bandit-learning-in","slug":"thompson-sampling-for-bandit-learning-in","title":"Thompson Sampling for Bandit Learning in Matching Markets","date":"2022-04-26","arxiv_id":"2204.12048","n_code_links":1,"syntology":null},{"paper":"/paper/vitpose-simple-vision-transformer-baselines","slug":"vitpose-simple-vision-transformer-baselines","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","date":"2022-04-26","arxiv_id":"2204.12484","n_code_links":6,"syntology":{"ran":18,"of":31,"n_ran_checked":12,"n_instrument":6,"unverified":13,"pointer_only":6,"phrase":"18 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 13 unverified","official":{"repos":["vitae-transformer/vitpose"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"crystal-transformer-self-learning-neural","title":"Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials","date":"2022-04-25","arxiv_id":"2204.11953","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-extrapolation-performance-of-dense","slug":"evaluating-extrapolation-performance-of-dense","title":"Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models","date":"2022-04-25","arxiv_id":"2204.11447","n_code_links":1,"syntology":null},{"paper":"/paper/groupwise-query-performance-prediction-with","slug":"groupwise-query-performance-prediction-with","title":"Groupwise Query Performance Prediction with BERT","date":"2022-04-25","arxiv_id":"2204.11489","n_code_links":1,"syntology":null},{"paper":null,"slug":"ocformer-one-class-transformer-network-for","title":"OCFormer: One-Class Transformer Network for Image Classification","date":"2022-04-25","arxiv_id":"2204.11449","n_code_links":0,"syntology":null},{"paper":null,"slug":"performer-a-novel-ppg-to-ecg-reconstruction","title":"Performer: A Novel PPG-to-ECG Reconstruction Transformer for a Digital Biomarker of Cardiovascular Disease Detection","date":"2022-04-25","arxiv_id":"2204.11795","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-real-time-scientific-experiments","slug":"predicting-real-time-scientific-experiments","title":"Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning","date":"2022-04-25","arxiv_id":"2204.11718","n_code_links":1,"syntology":null},{"paper":"/paper/swinfuse-a-residual-swin-transformer-fusion","slug":"swinfuse-a-residual-swin-transformer-fusion","title":"SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images","date":"2022-04-25","arxiv_id":"2204.11436","n_code_links":1,"syntology":null},{"paper":"/paper/emotion-aware-transformer-encoder-for-1","slug":"emotion-aware-transformer-encoder-for-1","title":"Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation","date":"2022-04-24","arxiv_id":"2204.11320","n_code_links":1,"syntology":null},{"paper":"/paper/faster-learned-sparse-retrieval-with-guided","slug":"faster-learned-sparse-retrieval-with-guided","title":"Faster Learned Sparse Retrieval with Guided Traversal","date":"2022-04-24","arxiv_id":"2204.11314","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-win-lottery-tickets-in-bert-1","slug":"learning-to-win-lottery-tickets-in-bert-1","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","date":"2022-04-24","arxiv_id":"2204.11218","n_code_links":1,"syntology":null},{"paper":"/paper/relvit-concept-guided-vision-transformer-for-1","slug":"relvit-concept-guided-vision-transformer-for-1","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","date":"2022-04-24","arxiv_id":"2204.11167","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":3,"n_instrument":3,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["NVlabs/RelViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"local-gaussian-process-extrapolation-for-bart","title":"Local Gaussian process extrapolation for BART models with applications to causal inference","date":"2022-04-23","arxiv_id":"2204.10963","n_code_links":0,"syntology":null},{"paper":null,"slug":"time-series-forecasting-tsf-using-various","title":"Time Series Forecasting (TSF) Using Various Deep Learning Models","date":"2022-04-23","arxiv_id":"2204.11115","n_code_links":0,"syntology":null},{"paper":"/paper/attentions-help-cnns-see-better-attention","slug":"attentions-help-cnns-see-better-attention","title":"Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network","date":"2022-04-22","arxiv_id":"2204.10485","n_code_links":3,"syntology":null},{"paper":null,"slug":"dfam-detr-deformable-feature-based-attention","title":"DFAM-DETR: Deformable feature based attention mechanism DETR on slender object detection","date":"2022-04-22","arxiv_id":"2204.10667","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-instance-discovery-vision-transformer","title":"Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition","date":"2022-04-22","arxiv_id":"2204.10731","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-symbolic-regression-with","slug":"end-to-end-symbolic-regression-with","title":"End-to-end symbolic regression with transformers","date":"2022-04-22","arxiv_id":"2204.10532","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/symbolicregression"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"fine-tuning-bert-models-to-classify","title":"Fine-Tuning BERT Models to Classify Misinformation on Garlic and COVID-19 on Twitter","date":"2022-04-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-label-wise-attention-transformer","slug":"hierarchical-label-wise-attention-transformer","title":"Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding","date":"2022-04-22","arxiv_id":"2204.10716","n_code_links":1,"syntology":null},{"paper":"/paper/hypergraph-transformer-weakly-supervised","slug":"hypergraph-transformer-weakly-supervised","title":"Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering","date":"2022-04-22","arxiv_id":"2204.10448","n_code_links":1,"syntology":null},{"paper":"/paper/libris2s-a-german-english-speech-to-speech","slug":"libris2s-a-german-english-speech-to-speech","title":"LibriS2S: A German-English Speech-to-Speech Translation Corpus","date":"2022-04-22","arxiv_id":"2204.10593","n_code_links":1,"syntology":null},{"paper":"/paper/spatiality-guided-transformer-for-3d-dense","slug":"spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","n_code_links":1,"syntology":null},{"paper":null,"slug":"taygete-at-semeval-2022-task-4-roberta-based","title":"Taygete at SemEval-2022 Task 4: RoBERTa based models for detecting Patronising and Condescending Language","date":"2022-04-22","arxiv_id":"2204.10519","n_code_links":0,"syntology":null},{"paper":"/paper/unified-pretraining-framework-for-document","slug":"unified-pretraining-framework-for-document","title":"Unified Pretraining Framework for Document Understanding","date":"2022-04-22","arxiv_id":"2204.10939","n_code_links":0,"syntology":null},{"paper":null,"slug":"wabert-a-low-resource-end-to-end-model-for","title":"WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment","date":"2022-04-22","arxiv_id":"2204.10461","n_code_links":0,"syntology":null},{"paper":null,"slug":"btranspose-bottleneck-transformers-for-human","title":"BTranspose: Bottleneck Transformers for Human Pose Estimation with Self-Supervised Pre-Training","date":"2022-04-21","arxiv_id":"2204.10209","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-artificial-intelligence-as-a","title":"Measuring artificial intelligence: a systematic assessment and implications for governance","date":"2022-04-21","arxiv_id":"2204.10304","n_code_links":0,"syntology":null},{"paper":"/paper/is-neural-topic-modelling-better-than-1","slug":"is-neural-topic-modelling-better-than-1","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","date":"2022-04-21","arxiv_id":"2204.09874","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hyintell/topicx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-tier-platform-for-cognizing-massive","title":"Multi-Tier Platform for Cognizing Massive Electroencephalogram","date":"2022-04-21","arxiv_id":"2204.09840","n_code_links":0,"syntology":null},{"paper":"/paper/sintra-learning-an-inspiration-model-from-a","slug":"sintra-learning-an-inspiration-model-from-a","title":"SinTra: Learning an inspiration model from a single multi-track music segment","date":"2022-04-21","arxiv_id":"2204.09917","n_code_links":1,"syntology":null}],"record_sha256":"5c96378b46caa207f72cf5132b8f55397360934d3b4be8e2dd33a888e22e0aeb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}